Unverified50% confidenceBenchmarkExact time
This benchmark uses 10 original short documents of 200 to 250 words each, with 18 planted anomalies, 37 scoring entries in total (18 dirty and 19 clean), testing 13 models with 74 prompts per model.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified该测试样本规模相对有限（5个模型、13个代码库），结论有待更大规模验证76% similarUnverified运行10次测试置信区间宽度约±31%，100次收窄至±10%，400次进一步收窄至±5%，推荐关键测试用例至少运行20-50次75% similarUnverifiedThe test suite consists of 10 benchmarks; most run 1,000 questions each, with HumanEval comprising 164 questions and TruthfulQA comprising 817 questions.74% similarUnverified19.4% (6,251 articles) of duplicate document contamination exists in the naive test set split.72% similarUnverifiedThe author used five real financial/payment documents and ten manually verified test questions to conduct a side-by-side comparison of four approaches: vector-only, BM25-only, hybrid retrieval without reranking, and the full ReRankEval pipeline.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1000258API
curl https://kongchang.com/api/v1/knowledge/claims/1000258MCP
get_claim(id=1000258)